Recently, Deep Convolutional Neural Networks (DCNNs) including the ResNet-20 architecture have been privately evaluated on encrypted, low-resolution data with the Residue-Number-System Cheon-Kim-Kim-Song (RNS-CKKS) homomorphic encryption scheme. We extend methods for evaluating DCNNs on images with larger dimensions and many channels, beyond what can be stored in single ciphertexts. Additionally, we simplify and improve the efficiency of the recently introduced multiplexed image format, demonstrating that homomorphic evaluation can work with standard, row-major matrix packing and results in encrypted inference time speedups by $4.6-6.5\times$. We also show how existing DCNN models can be regularized during the training process to further improve efficiency and accuracy. These techniques are applied to homomorphically evaluate a DCNN with high accuracy on the high-resolution ImageNet dataset for the first time, achieving $80.2\%$ top-1 accuracy. We also achieve the highest reported accuracy of homomorphically evaluated CNNs on the CIFAR-10 dataset of $98.3\%$.

翻译：近期，包括ResNet-20架构在内的深度卷积神经网络（DCNNs）已基于残数系统Cheon-Kim-Kim-Song（RNS-CKKS）同态加密方案，对加密的低分辨率数据实现了私有推理评估。我们扩展了方法，使其能够处理超出单个密文存储容量的、具有更大尺寸和多通道的图像上的DCNN评估。此外，我们简化并提升了近期提出的多路复用图像格式的效率，证明同态评估可与标准的行优先矩阵打包方式协同工作，并实现加密推理时间加速$4.6-6.5$倍。我们还展示了如何在训练过程中对现有DCNN模型进行正则化，以进一步提升效率与精度。这些技术首次被应用于高分辨率ImageNet数据集上的同态加密DCNN评估，实现了$80.2\%$的Top-1准确率。同时，我们在CIFAR-10数据集上取得了同态加密CNN评估的最高报告准确率$98.3\%$。